Image Signature Research Articles

Handwritten Signature Verification System Using User-dependent Approach: A Comparative Study

Handwritten signature verification is a critical aspect of personal authentication in numerous sectors, including banking, legal, and access control systems. This paper provides a comprehensive investigation into writer-dependent signature verification techniques, spanning from traditional approaches such as Histogram of Oriented Gradients (HOG) and Scale-Invariant Feature Transform (SIFT) to cutting-edge deep learning architectures like Siamese and triplet networks. Through extensive experimentation and meticulous analysis conducted on benchmark datasets, we rigorously compare and evaluate the efficacy of these approaches. Our study reveals intriguing insights into the performance characteristics of different methodologies, shedding light on their strengths, weaknesses, and areas for improvement. Notably, we observe that while traditional feature-based methods excel in capturing discriminative information from signature images, deep learning architectures offer enhanced flexibility and adaptability, particularly in scenarios with large and diverse datasets. By combining the strengths of both paradigms, we demonstrate the potential for building robust and reliable signature verification systems capable of handling real-world challenges and variations. We highlight the importance of carefully curated datasets and well-designed network architectures in achieving optimal results, thereby providing valuable guidelines for practitioners and researchers in the field. In conclusion, this study contributes significant insights to the advancement of handwritten signature verification systems, emphasizing the importance of leveraging both traditional methodologies and modern deep learning techniques for building secure and dependable authentication mechanisms. By addressing key challenges and exploring novel approaches, our research aims to foster innovation and enhance the security measures associated with handwritten signature authentication in diverse applications. Keywords—Handwritten signature verification, Writer-dependent approach, Feature-based methods, Deep learning, Siamese networks, Triplet networks, Benchmark datasets, Performance evaluation, Authentication mechanisms, Security measures.

Signature Fraud Detection Using Deep Learning

The use of signatures for personal identification and verification is quite common. Signatures are validated for many documents such as Bank cheques and legal transactions. The necessity for effective automated solutions for signature verification has grown as signatures are now a prerequisite for both authorization and authentication in legal activities. Two images—the original signature and the test signature—are used as input in this process. To determine whether the signature is fake or not, the characteristics that were extracted are compared, and the difference in error values between them is examined. The growing digital landscape has increased the need for robust and efficient fraud detection systems. This project presents a unique approach to detecting signature fraud using deep learning techniques, specifically employing Siamese Neural Networks, implemented in Python. With a dataset comprising 2149 signature images, encompassing both genuine and fraudulent samples from Dutch users, our model demonstrates remarkable accuracy. The Siamese Neural Network architecture excels in signature verification tasks by learning to distinguish between genuine and fraudulent signatures through contrastive learning. The key achievement of this project is the exceptional accuracy levels attained during the training and validation phases. The model's training accuracy stands at an impressive 98.00%, while the validation accuracy reaches an astonishing 99.00%. These high accuracy rates are a testament to the effectiveness of Siamese Neural Networks in signature fraud detection. In a world where the security of digital signatures is paramount, this project showcases the power of deep learning and Siamese Neural Networks in safeguarding against fraudulent activities. The model's success in accurately distinguishing between authentic and forged signatures offers promising potential for enhancing security measures in various domains, including finance, legal, and document management.

Differentiation and characterization of healthy versus pathological tau using chemical exchange saturation transfer.

Neurofibrillary tangles of tau constitute one of the key biological hallmarks of Alzheimer's disease. Currently, the assessment of regional tau accumulation requires intravenous administration of radioactive tracers for PET imaging. A noninvasive MRI-based solution would have significant clinical implications. Herein, we utilized an MRI technique known as chemical exchange saturation transfer (CEST) to determine the imaging signature of tau in both its monomeric and pathologic fibrillated conformations. Three sets of purified recombinant full-length (4R) tau protein were prepared for collection of CEST spectra using a 9.4 T NMR spectrometer at varying temperatures (25, 37, and 42°C) and RF intensities (0.7, 1.0, 1.5, and 2.2 μT). Monomeric and fibrillated tau were readily distinguished based on their Z-spectrum profiles. Fibrillated tau demonstrated a less prominent peak at 3.5 ppm with additional peaks near 0.5 and 1.5 ppm. No significant differences were identified between fibrillated tau prepared using heparin versus seed-competent tau. In conclusion, monomeric and fibrillated tau can be readily detected and distinguished based on their CEST-derived Z-spectra, pointing to the potential utility of CEST-MRI as a noninvasive biomarker of regional pathologic tau accumulation in the brain. Further testing and validation in vitro and in vivo will be necessary before this can be applied clinically.

A neurofunctional signature of subjective disgust generalizes to oral distaste and socio-moral contexts.

While disgust originates in the hard-wired mammalian distaste response, the conscious experience of disgust in humans strongly depends on subjective appraisal and may even extend to socio-moral contexts. Here, in a series of studies, we combined functional magnetic resonance imaging with machine-learning-based predictive modelling to establish a comprehensive neurobiological model of subjective disgust. The developed neurofunctional signature accurately predicted momentary self-reported subjective disgust across discovery (n = 78) and pre-registered validation (n = 30) cohorts and generalized across core disgust (n = 34 and n = 26), gustatory distaste (n = 30) and socio-moral (unfair offers; n = 43) contexts. Disgust experience was encoded in distributed cortical and subcortical systems, and exhibited distinct and shared neural representations with subjective fear or negative affect in interoceptive-emotional awareness and conscious appraisal systems, while the signatures most accurately predicted the respective target experience. We provide an accurate functional magnetic resonance imaging signature for disgust with a high potential to resolve ongoing evolutionary debates.

Photoelectron Imaging Signature for Selective Formation of Icosahedral Anionic Silver Cages Encapsulating Group 5 Elements: M@Ag12- (M = V, Nb, and Ta).

An assembly of 13 atoms can form highly symmetric architectures like those belonging to D3h, Oh, D5h, and Ih point groups. Here, using photoelectron imaging spectroscopy in combination with density functional theory (DFT) calculations, we present a simple yet convincing experimental signature for the selective formation of icosahedral cages of anionic silver clusters encapsulating a dopant atom of group 5 elements: M@Ag12- (M = V, Nb, and Ta). Their photoelectron images obtained at 4 eV closely resemble one another: only a single ring is observed, which is assignable to photodetachment signals from a 5-fold degenerate superatomic 1D electronic shell in the 1S21P61D10 configuration of valence electrons. The perfect degeneracy represents an unambiguous fingerprint of an icosahedral symmetry, which would otherwise be lifted in all of the other structural isomers. DFT calculations confirm that Ih forms are the most stable and that D5h, Oh, and D3h structures are not found even in metastable states.

Handwritten online signature verification and Forgery Detection for Online Handwritten Signature using Hybrid Wavelet Transform-1 with HMM classifier

Online signature verification employs a distinctive biometric trait by utilizing both static and dynamic features extracted from 2D signature images. A hybrid wavelet transform, denoted as HWT-1 with a size of 256, is formed through the Kronecker product of two orthogonal transforms, such as DCT, DHT, Haar, Hadamard, and Kekre, each with sizes 4 and 64. This HWT facilitates signal analysis at both global and local levels, akin to traditional wavelet transforms. Specifically, HWT-1 processes the 256 samples of online handwritten signatures, yielding 128 samples that constitute the feature vectors for signature verification and forgery detection. These feature vectors are then inputted into the Left-Right and Ergodic Hidden Markov Model (HMM) classifiers for further analysis. The HMMs are trained using 10 randomly selected genuine signature samples and subsequently tested with the remaining 10 genuine signatures and 20 forged signatures from the SVC 2004 signature database, repeating this process 20 times to compute average values. Among all possible combinations of HWT-1 utilizing DCT, DHT, Haar, Hadamard, and Kekre transforms for the Left-Right HMM model, the combination of DCT 4 and Haar 64 demonstrates the best performance with a False Rejection Rate (FRR) and False Acceptance Rate (FAR) of 1.05% and 0.99%, respectively, at state 3. Similarly, considering all feasible combinations of HWT-1 for the Ergodic HMM model, the combination of DCT 4 and Kekre 64 yields the optimal performance with an FRR and FAR of 1.24% and 1.33%, respectively, at state 3.

Handwritten Online Signature Verification and Forgery Detection Using Hybrid Wavelet Transform-2 with HMM Classifier

Online signature verification stands out as a distinctive biometric feature, offering both static and dynamic attributes within 2D signature images. A Hybrid Wavelet Transform-2 (HWT-2) with a size of 256 is constructed by employing the Kronecker product of two orthogonal transforms: DCT, DHT, Haar, Hadamard, and Kekre, each with sizes of 4 and 64. The HWT enables the analysis of signals at both global and local levels, akin to wavelet transforms. HWT-2 is applied to 256 samples of online handwritten signatures, and the first 128 samples of the output are utilized as feature vectors for the verification and forgery detection of online handwritten signatures. These feature vectors are inputted into Left-Right and Ergodic Hidden Markov Model (HMM) classifiers for analysis. The HMMs are trained using 10 randomly selected genuine signature samples, and subsequently tested on the remaining 10 genuine signatures and 20 forged signatures from 40 users of the SVC 2004 signature database. This process is repeated 20 times, and the average values are computed. Among all possible combinations of HWT-2 using DCT, DHT, Haar, Hadamard, and Kekre transforms for the Left-Right HMM model, the combination of DCT 4 and DHT 64 demonstrates the best performance, with False Rejection Rate (FRR) and False Acceptance Rate (FAR) values of 3.96% and 1.48%, respectively, for state 5. Similarly, for the Ergodic HMM model, the combination of DCT 4 and DHT 64 exhibits the best performance, with FRR and FAR values of 1.10% and 2.88%, respectively, for state 5. These results indicate that combinations of HWT-2 outperform individual orthogonal transforms, and further, that HWT-2 combinations within the Ergodic HMM model offer superior performance compared to the Left-Right HMM model.

Comparative Analysis of Handwritten Online Signature Verification and Forgery Detection Using Hybrid Wavelet Transform-1 and 2 with HMM Classifier

Online signature verification is a unique biometric feature. Provides static and dynamic features for 2D signature images. Hybrid wavelet transform -1 and 2 (HWT-1 and HWT-2) of size 256 is created using the Kronecker product of two orthogonal transforms such as DCT, DHT, Haar, Hadamard and Kekre with size 4 and 64. HWT has the ability to analyze signals such as wavelet transform at global and local levels. HWT-1 and HWT-2 are used for the 256 samples of the online Handwritten signature and the first 128 samples of the output are used as feature vectors for handwritten online signature verification and forgery detection. This feature vector is given to the Left-Right and Ergodic modelled HMM classifier for analysis. HMM is trained using 10 randomly chosen genuine signature samples and is used to test remaining 10 genuine signatures and 20 forged signatures of 40 users of SVC 2004 signature database. This process is iterated 20 times and then average values are calculated. Considering all the possible combination of HWT-1 and HWT-2 for DCT, DHT, Haar, Hadamard and Kekre transform for Left Right HMM model, DCT 4 Haar 64 HWT-1 offers best performance of FRR, FAR of 1.05%, 0.99% respectively for state 3. Considering all the possible combination of HWT-1 and HWT-2 for DCT, DHT, Haar, Hadamard and Kekre transform for Ergodic HMM model, DCT 4 DHT 64 offers best performance of FRR, FAR of 1.10%, 2.88% respectively for state 5. We conclude that comparing HWT-1 and HWT-2 combinations for Left Right and Ergodic HMM model, HWT-1 for Left Right model offer better performance.

Signature Verification System Using Deep Learning

The proposed system employs a convolutional neural network (CNN) architecture for signature feature extraction and classification. Furthermore, the system integrates preprocessing modules for signature image normalization, noise reduction, and feature extraction to enhance the robustness and accuracy of the verification process. Extensive experimentation and evaluation are conducted on benchmark datasets, including the widely used Tobacco 800 dataset and Kaggle dataset, to assess the performance of the proposed system in terms of accuracy, precision, recall, and score metrics. The results demonstrate the effectiveness and robustness of the deep learning-based signature verification system in accurately distinguishing between genuine and forged signatures.

Noninvasive Autopsy-Validated Tumor Probability Maps Identify Glioma Invasion Beyond Contrast Enhancement.

This study identified a clinically significant subset of patients with glioma with tumor outside of contrast enhancement present at autopsy and subsequently developed a method for detecting nonenhancing tumor using radio-pathomic mapping. We tested the hypothesis that autopsy-based radio-pathomic tumor probability maps would be able to noninvasively identify areas of infiltrative tumor beyond traditional imaging signatures. A total of 159 tissue samples from 65 subjects were aligned to MRI acquired nearest to death for this retrospective study. Demographic and survival characteristics for patients with and without tumor beyond the contrast-enhancing margin were computed. An ensemble algorithm was used to predict pixelwise tumor presence from pathological annotations using segmented cellularity (Cell), extracellular fluid, and cytoplasm density as input (6 train/3 test subjects). A second level of ensemble algorithms was used to predict voxelwise Cell, extracellular fluid, and cytoplasm on the full data set (43 train/22 test subjects) using 5-by-5 voxel tiles from T1, T1 + C, fluid-attenuated inversion recovery, and apparent diffusion coefficient as input. The models were then combined to generate noninvasive whole brain maps of tumor probability. Tumor outside of contrast was identified in 41.5% of patients, who showed worse survival outcomes (hazard ratio = 3.90, P < .001). Tumor probability maps reliably tracked nonenhancing tumor on a range of local and external unseen data, identifying tumor outside of contrast in 69% of presurgical cases that also showed reduced survival outcomes (hazard ratio = 1.67, P = .027). This study developed a multistage model for mapping gliomas using autopsy tissue samples as ground truth, which was able to identify regions of tumor beyond traditional imaging signatures.

Noninvasive Stratification of Colon Cancer by Multiplex PET Imaging.

The current approach for molecular subtyping of colon cancer relies on gene expression profiling, which is invasive and has limited ability to reveal dynamics and spatial heterogeneity. Molecular imaging techniques, such as PET, present a noninvasive alternative for visualizing biological information from tumors. However, the factors influencing PET imaging phenotype, the suitable PET radiotracers for differentiating tumor subtypes, and the relationship between PET phenotypes and tumor genotype or gene expression-based subtyping remain unknown. In this study, we conducted 126 PET scans using four different metabolic PET tracers, [18F]fluorodeoxy-D-glucose ([18F]FDG), O-(2-[18F]fluoroethyl)-l-tyrosine ([18F]FET), 3'-deoxy-3'-[18F]fluorothymidine ([18F]FLT), and [11C]acetate ([11C]ACE), using a spectrum of five preclinical colon cancer models with varying genetics (BMT, AKPN, AK, AKPT, KPN), at three sites (subcutaneous, orthograft, autochthonous) and at two tumor stages (primary vs. metastatic). The results demonstrate that imaging signatures are influenced by genotype, tumor environment, and stage. PET imaging signatures exhibited significant heterogeneity, with each cancer model displaying distinct radiotracer profiles. Oncogenic Kras and Apc loss showed the most distinctive imaging features, with [18F]FLT and [18F]FET being particularly effective, respectively. The tissue environment notably impacted [18F]FDG uptake, and in a metastatic model, [18F]FET demonstrated higher uptake. By examining factors contributing to PET-imaging phenotype, this study establishes the feasibility of noninvasive molecular stratification using multiplex radiotracer PET. It lays the foundation for further exploration of PET-based subtyping in human cancer, thereby facilitating noninvasive molecular diagnosis.

NAISS: A reverse proxy approach to mitigate MageCart's e-skimmers in e-commerce

The rise of payment details theft has led to increasing concerns regarding the security of e-commerce platforms. For the MageCart threat family, the attacks employ e-skimmers, which are pieces of software code that instruct clients to forward payment details to an attacker-controlled server. They can be injected into hosting providers' servers as HTML tags such as script, iframe, and img. By leveraging image steganography - the technique of hiding structured information inside images without visual perturbances - MageCart groups can deliver e-skimmers without raising suspicion. In this work, we systematically review applicable solutions in the literature and evaluate their drawbacks in the setting of a compromised hosting provider. While promising, existing solutions in the literature present shortcomings such as a lack of compatibility, adaptability, or functionality in the presence of an attacker. Based on this review, we compile a set of features for a better solution, which we use as a foundation for designing our proposed solution - NAISS: Network Authentication of Images to Stop e-Skimmers. Through our solution, digital signatures of individual images are checked inside a server-side middlebox residing in the hosting provider's network to prevent the transmission of unauthorized images to clients. Elliptic curve signatures are provided by the e-commerce platform developer prior to uploading a website to the hosting provider. Our proof-of-concept implementation shows that NAISS is capable of filtering 100% of present stegoimages, regardless of their novelty, while imposing a minimal performance detriment and no client-side modifications.

Region adjacency graph based GNN approach for static signature classification

Graph Neural Networks (GNNs) have gained popularity across various research fields in recent years. GNNs utilize graphs to construct an embedding that includes details about the nodes and edges in a graph’s neighborhood. In this work, a set of Region Adjacency Graphs (RAG) derives the attribute values from Static Signature (SS) images. These attribute values are used to label the nodes of the complete graph, which is formed by considering each signature as a node taken from the sample of signatures of a specific signer. The complete graph is trained by using GraphSAGE, an inductive representation learning method. This trained model helps to determine any newly introduced node (static signature to be tested) as genuine or fake. Standard static signature datasets, notably GPDSsynthetic and MCYT-75 are used to test the prevailing model. Experimental results on genuine and counterfeit signature networks demonstrate that our computed model enables a high rate of accuracy (GPDSsynthetic 99.91% and MCYT-75 99.56%) and minimum range of loss (GPDSsynthetic 0.0061 and MCYT-75 0.0070) on node classification.

Incidental Ring-hyperenhancing Liver Micronodules at CT Hepatic Arteriography-guided Percutaneous Thermal Ablation of Colorectal Liver Metastases.

CT during hepatic arteriography (CTHA) is a highly sensitive imaging method for detecting colorectal liver metastases (CLMs), which supports its use during percutaneous thermal liver ablation. In contrast to its high sensitivity, its specificity for incidental small CLMs not detected at preablation cross-sectional imaging is believed to be low given the absence of specific imaging signatures and the common presence of pseudolesions. In this retrospective study of 22 patients (mean age, 55 years ± 10.6 [SD]; 63.6% male, 36.4% female) with CLMs undergoing CTHA-guided microwave percutaneous thermal ablation between November 2017 and October 2022, the authors provided a definition of incidental ring-hyperenhancing liver micronodules (RHLMs) and investigated whether there is a correlation of RHLMs with histologic analysis or intrahepatic tumor progression at imaging follow-up after applying a biomechanical deformable image registration method. The analysis revealed 25 incidental RHLMs in 41.7% (10 of 24) of the CTHA images from the respective guided ablation sessions. Of those, four RHLMs were ablated. Among the remaining 21 RHLMs, 71.4% (15 of 21) were confirmed to be CLM with either histology (n = 3) or imaging follow-up (n = 12). The remaining 28.6% (six of 21) of RHLMs were not observed at follow-up imaging. This suggests that RHLMs at CTHA may be an early indicator of incidental small CLMs. Keywords: Colorectal Neoplasms, Liver, Angiography, CT, Incidental Findings, Ablation Supplemental material is available for this article. © RSNA, 2024.

Imaging signatures in diffuse choroidal hemangioma in a case of sturge weber syndrome

Sturge–Weber syndrome (SWS) is a rare congenital neurocutaneous disorder characterized by facial port-wine stain, leptomeningeal hemangiomas, and ocular manifestations such as glaucoma and diffuse choroidal hemangioma (DCH). DCH is a benign vascular lesion characteristically seen in up to 50% of patients affected with SWS. Diffuse choroidal hemangioma can cause refractive error, foveal distortion, and exudative retinal detachment and contribute to vision loss. We report a case of a young male with SWS and a unilateral DCH with characteristic imaging features.

Predicting Lipid-Rich Plaque Progression in Coronary Arteries Using Multimodal Imaging and Wall Shear Stress Signatures.

Plaque composition and wall shear stress (WSS) magnitude act as well-established players in coronary plaque progression. However, WSS magnitude per se does not completely capture the mechanical stimulus to which the endothelium is subjected, since endothelial cells experience changes in the WSS spatiotemporal configuration on the luminal surface. This study explores WSS profile and lipid content signatures of plaque progression to identify novel biomarkers of coronary atherosclerosis. Thirty-seven patients with acute coronary syndrome underwent coronary computed tomography angiography, near-infrared spectroscopy intravascular ultrasound, and optical coherence tomography of at least 1 nonculprit vessel at baseline and 1-year follow-up. Baseline coronary artery geometries were reconstructed from intravascular ultrasound and coronary computed tomography angiography and combined with flow information to perform computational fluid dynamics simulations to assess the time-averaged WSS magnitude (TAWSS) and the variability in the contraction/expansion action exerted by WSS on the endothelium, quantifiable in terms of topological shear variation index (TSVI). Plaque progression was measured as intravascular ultrasound-derived percentage plaque atheroma volume change at 1-year follow-up. Plaque composition information was extracted from near-infrared spectroscopy and optical coherence tomography. Exposure to high TSVI and low TAWSS was associated with higher plaque progression (4.00±0.69% and 3.60±0.62%, respectively). Plaque composition acted synergistically with TSVI or TAWSS, resulting in the highest plaque progression (≥5.90%) at locations where lipid-rich plaque is exposed to high TSVI or low TAWSS. Luminal exposure to high TSVI, solely or combined with a lipid-rich plaque phenotype, is associated with enhanced plaque progression at 1-year follow-up. Where plaque progression occurred, low TAWSS was also observed. These findings suggest TSVI, in addition to low TAWSS, as a potential biomechanical predictor for plaque progression, showing promise for clinical translation to improve patient prognosis.

A hybrid multimodal machine learning model for Detecting Alzheimer's disease

Alzheimer's disease (AD) diagnosis utilizing single modality neuroimaging data has limitations. Multimodal fusion of complementary biomarkers may improve diagnostic performance. This study proposes a multimodal machine learning framework integrating magnetic resonance imaging (MRI), positron emission tomography (PET) and cerebrospinal fluid (CSF) assays for enhanced AD characterization. The model incorporates a hybrid algorithm combining enhanced Harris Hawks Optimization (HHO) algorithm referred to as ILHHO, with Kernel Extreme Learning Machine (KELM) classifier for simultaneous feature selection and classification. ILHHO enhances HHO's search efficiency by integrating iterative mapping (IM) to improve population diversity and local escaping operator (LEO) to balance exploration-exploitation. Comparative analysis with other improved HHO algorithms, classic meta-heuristic algorithms (MHAs), and state-of-the-art MHAs on IEEE CEC2014 benchmark functions indicates that ILHHO achieves superior optimization performance compared to other comparative algorithms. The synergistic ILHHO-KELM model is evaluated on 202 AD Neuroimaging Initiative (ADNI) subjects. Results demonstrate superior multimodal classification accuracy over single modalities, validating the importance of fusing heterogeneous biomarkers. MRI + PET + CSF achieves 99.2 % accuracy for AD vs. normal control (NC), outperforming conventional and proposed methods. Discriminative feature analysis provides further insights into differential AD-related neurodegeneration patterns detected by MRI and PET. The differential PET and MRI features demonstrate how the two modalities provide complementary biomarkers. The neuroanatomical relevance of selected features supports ILHHO-KELM's potential for extracting sensitive AD imaging signatures. Overall, the study showcases the advantages of capitalizing on complementary multimodal data through advanced feature learning techniques for improving AD diagnosis.

Gene-SGAN: discovering disease subtypes with imaging and genetic signatures via multi-view weakly-supervised deep clustering

Disease heterogeneity has been a critical challenge for precision diagnosis and treatment, especially in neurologic and neuropsychiatric diseases. Many diseases can display multiple distinct brain phenotypes across individuals, potentially reflecting disease subtypes that can be captured using MRI and machine learning methods. However, biological interpretability and treatment relevance are limited if the derived subtypes are not associated with genetic drivers or susceptibility factors. Herein, we describe Gene-SGAN – a multi-view, weakly-supervised deep clustering method – which dissects disease heterogeneity by jointly considering phenotypic and genetic data, thereby conferring genetic correlations to the disease subtypes and associated endophenotypic signatures. We first validate the generalizability, interpretability, and robustness of Gene-SGAN in semi-synthetic experiments. We then demonstrate its application to real multi-site datasets from 28,858 individuals, deriving subtypes of Alzheimer’s disease and brain endophenotypes associated with hypertension, from MRI and single nucleotide polymorphism data. Derived brain phenotypes displayed significant differences in neuroanatomical patterns, genetic determinants, biological and clinical biomarkers, indicating potentially distinct underlying neuropathologic processes, genetic drivers, and susceptibility factors. Overall, Gene-SGAN is broadly applicable to disease subtyping and endophenotype discovery, and is herein tested on disease-related, genetically-associated neuroimaging phenotypes.

Verifiable visually meaningful image encryption algorithm based on compressive sensing and (t, n)-threshold secret sharing

Abstract A verifiable visually meaningful image encryption algorithm based on compressive sensing and (t, n)-threshold secret sharing is proposed. Firstly, the plain image is compressed and encrypted by 2D block compressive sensing to obtain the pre-encrypted image. During this process, the enhanced logistic map and the enhanced tent map are used to generate the measurement matrix and the permutation sequence, respectively. Secondly, multiple shadow images of the pre-encrypted image are generated by using the (t, n)-threshold secret sharing scheme, and then each shadow image is further encrypted by using the encryption matrix generated by the chaotic system. Meanwhile, the signatures of the shadow images are obtained by using RSA signature algorithm. Finally, the shadow images and their corresponding signatures are embedded into the carrier image to generate the cipher image with high visual quality by using the LSB method. Additionally, the present algorithm can resist known-plaintext and chosen-plaintext attacks by incorporating the hash value of the plain image as part of the key. Meanwhile, the use of 2D block compressive sensing significantly reduces the reconstruction time. Simulation results demonstrate that the proposed algorithm achieves excellent decryption quality and operational efficiency.

Classification of Small Drones Using Low-Uncertainty Micro-Doppler Signature Images and Ultra-Lightweight Convolutional Neural Network.

Many studies have attempted to classify small drones in response to threats posed by the technical progress of small drones. Recently, small drones have been classified utilizing convolutional neural networks (CNNs) with micro-Doppler signature (MDS) images generated from frequency-modulated continuous-wave (FMCW) radars. This study proposes a comprehensive method for classifying small drones in real-time using high-quality MDS images and an ultra-lightweight CNN. The proposed comprehensive method comprises an MDS image generation technique, which can improve the quality of MDS images generated via FMCW radars, and the ultra-lightweight CNN with high accuracy performance despite its remarkable lightness. Experimental results show that the proposed MDS image generation technique increases the accuracy of CNNs by enhancing the MDS image quality. This is further verified using the results of uncertainty quantification. The proposed ultra-lightweight CNN significantly decreases the computational cost while achieving high accuracy. Finally, we demonstrate that the proposed comprehensive method successfully classifies small drones from far distances with high efficiency and accuracy: the maximum and average accuracies for classification are 100% and 99.21%, respectively, and the numbers of parameters, nodes, and floating-point operations of the proposed ultra-lightweight CNN are approximately 4.88 K, 21.51 K, and 31.52 M, respectively.